{
  "markdown": "# Zhijian Skills\n\n<p align=\"center\">\n  <img src=\"./assets/readme/portfolio-hero.svg\" width=\"100%\" alt=\"Zhijian Skills: one canonical portfolio of nineteen focused Agent Skills\">\n</p>\n\n<p align=\"center\"><strong>Install focused Agent Skills from one trusted source, with complete payloads and independently verified releases.</strong></p>\n\n<p align=\"center\">\n  <a href=\"./README.zh-CN.md\">简体中文</a> ·\n  <a href=\"#choose-a-skill\">Browse the catalog</a> ·\n  <a href=\"./CONTRIBUTING.md\">Contribute</a>\n</p>\n\nZhijian Skills is the canonical source for nineteen focused Agent Skills spanning Codex operations and experience, workflow orchestration, model reasoning and infrastructure, knowledge systems, research, information design, and publishing.\n\n## Start in 30 seconds\n\nList all nineteen Skills:\n\n```bash\nnpx skills add zjp1997720/zhijian-skills --list\n```\n\nInstall only what you need:\n\n```bash\nnpx skills add zjp1997720/zhijian-skills --skill wechat-styler\n```\n\nInstall globally for a specific Harness:\n\n```bash\nnpx skills add zjp1997720/zhijian-skills \\\n  --skill codex-model-routing-team --agent codex --global --copy --yes\n```\n\n> This is the only publishing repository. New Skills, releases, Issues, and contributions all belong here.\n\n## Add the WorkBuddy marketplace\n\nOpen **Experts · Skills · Connectors → Skills → Bundles → Add marketplace** and enter:\n\n```text\nzjp1997720/zhijian-skills\n```\n\nThe full Git URL `https://github.com/zjp1997720/zhijian-skills.git` also works. Select `zhijian-skills` after adding it and install individual bundles as needed. Adding the marketplace does not install every Skill.\n\nUse the repository URL, not a `/tree/main/skills` web page or raw JSON URL. Git distribution preserves each complete Skill payload, including scripts, references, and assets.\n\nCatalog availability does not imply WorkBuddy runtime compatibility. Entries marked `需 Codex 宿主能力` require Codex host capabilities. Other entries may still require local CLIs, authentication, or dependencies; consult their documentation. This adapter does not change those requirements.\n\nMaintainers: the catalog is generated from `registry/skills.json` and existing Chinese documentation. Run `python3 scripts/build_workbuddy_marketplace.py` after catalog/version changes; CI checks for drift.\n\nThe manifests and repository-local symlinks under `plugins/` are generated; editable Skill source remains under `skills/`. Installation materializes the links into complete files. Git checkouts must support symlinks. Verified with macOS WorkBuddy; Windows has not been tested. Run `python3 scripts/verify_workbuddy_install.py --cli <WorkBuddy-bundled-codebuddy>` to check installation, cold-start discovery, and payload hashes in a temporary config. Add `--source zjp1997720/zhijian-skills` to verify the public source.\n\n## Choose a Skill\n\n| Area | Skill | Result | Documentation |\n| --- | --- | --- | --- |\n| Model infrastructure | [`codex-cli-model-bridge`](docs/skills/codex-cli-model-bridge/README.md) | Add verified loopback models to Codex without hiding ChatGPT history | [Docs](docs/skills/codex-cli-model-bridge/README.md) |\n| Codex control | [`codex-doctor`](docs/skills/codex-doctor/README.md) | Diagnose context, configuration, and workspace drift without changing files | [Docs](docs/skills/codex-doctor/README.md) |\n| Cross-agent handoff | [`codex-external-handoff`](docs/skills/codex-external-handoff/README.md) | Launch and supervise persistent Codex App Server threads from WorkBuddy or Claude Code | [Docs](docs/skills/codex-external-handoff/README.md) |\n| Codex control | [`codex-handoff`](docs/skills/codex-handoff/README.md) | Continue an oversized or slow Codex task in a fresh task with compact context | [Docs](docs/skills/codex-handoff/README.md) |\n| Image generation | [`codex-image-gen`](docs/skills/codex-image-gen/README.md) | Reuse the logged-in Codex CLI OAuth state to generate and edit images without an API key | [Docs](docs/skills/codex-image-gen/README.md) |\n| Codex control | [`codex-model-routing-team`](docs/skills/codex-model-routing-team/README.md) | Compile parallel work into TeamPlans; use Luna for specified execution and Sol for unresolved judgment | [Docs](docs/skills/codex-model-routing-team/README.md) |\n| Codex control | [`codex-skill-admin`](docs/skills/codex-skill-admin/README.md) | Audit, disable, restore, and verify local Codex Skills | [Docs](docs/skills/codex-skill-admin/README.md) |\n| Codex experience | [`codex-theme-studio`](docs/skills/codex-theme-studio/README.md) | Build reversible macOS Codex themes from safe variables, custom artwork, or bundled presets | [Docs](docs/skills/codex-theme-studio/README.md) |\n| Knowledge systems | [`enterprise-clone-builder`](docs/skills/enterprise-clone-builder/README.md) | Build a structured enterprise digital-twin repository from evidence | [Docs](docs/skills/enterprise-clone-builder/README.md) |\n| Model reasoning | [`gpt56-sol-pro-consult`](docs/skills/gpt56-sol-pro-consult/README.md) | Get a file-grounded, model-verified GPT 5.6 Sol Pro second opinion through Codex Chrome | [Docs](docs/skills/gpt56-sol-pro-consult/README.md) |\n| Information design | [`html-express`](docs/skills/html-express/README.md) | Turn dense material into a clear, self-contained HTML report | [Docs](docs/skills/html-express/README.md) |\n| Long-form writing | [`leadbook`](docs/skills/leadbook/README.md) | Produce evidence-backed Chinese business books and white papers with auditable quality gates | [Docs](docs/skills/leadbook/README.md) |\n| Workflow orchestration | [`light-plan-and-work`](docs/skills/light-plan-and-work/README.md) | Plan bounded work briefly, execute immediately, and escalate only on heavy conditions | [Docs](docs/skills/light-plan-and-work/README.md) |\n| Release governance | [`skill-open-sourcer`](docs/skills/skill-open-sourcer/README.md) | Audit, package, document, verify, and publish Agent Skills | [Docs](docs/skills/skill-open-sourcer/README.md) |\n| Content research | [`wechat-article-search`](docs/skills/wechat-article-search/README.md) | Discover WeChat public-account articles as structured JSON | [Docs](docs/skills/wechat-article-search/README.md) |\n| Editorial publishing | [`wechat-styler`](docs/skills/wechat-styler/README.md) | Convert Markdown into polished, WeChat-compatible inline HTML | [Docs](docs/skills/wechat-styler/README.md) |\n| Content archiving | [`web-clipper`](docs/skills/web-clipper/README.md) | Save public article URLs and bounded archive pages as structured Markdown | [Docs](docs/skills/web-clipper/README.md) |\n| Model infrastructure | [`workbuddy-cli-model-bridge`](docs/skills/workbuddy-cli-model-bridge/README.md) | Connect verified CLI subscription models to WorkBuddy through a loopback proxy | [Docs](docs/skills/workbuddy-cli-model-bridge/README.md) |\n| Content archiving | [`wxmp-article-harvester`](docs/skills/wxmp-article-harvester/README.md) | Export a public WeChat account into verified Markdown, indexes, and a completion report | [Docs](docs/skills/wxmp-article-harvester/README.md) |\n\n## Why one Portfolio\n\n- **One editable source.** Every public Skill is maintained on `main` in this repository.\n- **Complete installation units.** Supporting scripts, references, themes, and assets travel with each Skill.\n- **Independent versions, one repository.** Every Skill owns its version, Changelog, canonical Tag, and tests while sharing this publishing source.\n\n`codex-model-routing-team` can be invoked explicitly. Its documentation also includes an optional `AGENTS.md` authorization block for automatic activation when parallel execution has a clear net benefit.\n\n## Repository model\n\n```text\nskills/<name>/          complete agent-facing install payload\ndocs/skills/<name>/     human-facing English and Chinese documentation\nregistry/skills.json    versions, validation, capabilities, and Harness support\nassets/readme/          Portfolio identity assets\n```\n\nEvery install and release resolves through this repository. The Portfolio does not create or synchronize standalone Skill repositories.\n\n## Contribution and license\n\nRead [CONTRIBUTING.md](CONTRIBUTING.md) before opening an Issue or pull request. The Portfolio is released under the [MIT License](LICENSE); bundled Skill notices remain with their respective payloads.\n",
  "bytes": 8285,
  "sha": "4bde852c1e4ca4b614fecd6fd8aeec0f6ed09bf66806d314fddffb82e72ada3a",
  "repo_slug": "zjp1997720/zhijian-skills",
  "fonte": "repo",
  "truncated": false,
  "api": "https://api.agentalog.com/api/listings/skl_zjp1997720_zhijian_skills_wechat_article_74c3ce39/readme"
}